INDEX

Explanations

references to academic journal articles and their citations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ãºa

-0.17

ua

-0.16

reu

-0.15

 Stub

-0.15

ĶåĽŀ

-0.14

.Layer

-0.13

ynam

-0.13

 convers

-0.13

.getCurrentUser

-0.13

agna

-0.13

POSITIVE LOGITS

anter

0.15

 jenter

0.14

andon

0.14

uma

0.14

 ficken

0.14

ìķĶ

0.14

Asi

0.14

imoto

0.14

IRON

0.14

rze

0.14

Activations Density 0.030%

references to academic journal articles and their citations

No Comments

No Known Activations